TEST #126 RESULTS
03/28/2025 - 10:07 PM
ACCELERATOR
MODEL
235
tokens/s
generation
172
ms
time to first token
7901
tokens/s
prompt
2208
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Xeon CPU E5-2650 v4 @ 2.20GHz (broadwell)
RAM
62.6GB
OS
Linux
Kernel Release
6.8.0-45-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #45~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Sep 11 15:25:05 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10959
tokens/s
222
tokens/s
98
ms
pp4096+tg256
6959
tokens/s
210
tokens/s
593
ms
pp2048+tg256
9396
tokens/s
244
tokens/s
222
ms
pp2048+tg768
9382
tokens/s
235
tokens/s
223
ms
pp1024+tg1024
5011
tokens/s
235
tokens/s
208
ms
pp1280+tg3072
10177
tokens/s
220
tokens/s
131
ms
pp384+tg1152
12489
tokens/s
240
tokens/s
35
ms
pp64+tg1024
6030
tokens/s
245
tokens/s
15
ms
pp16+tg1536
708
tokens/s
260
tokens/s
26
ms